Google Git
Sign in
linux / virt / kvm / kvm / 79cc6cdb932a5cf1a1ee05f6de12a7d102818d21 / . / arch / arm64 / kvm / sys_regs.c
blob: 1d84bc3396cbc658ed0ea65da91ba8013c01467f [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2012,2013 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*
* Derived from arch/arm/kvm/coproc.c:
* Copyright (C) 2012 - Virtual Open Systems and Columbia University
* Authors: Rusty Russell <rusty@rustcorp.com.au>
* Christoffer Dall <c.dall@virtualopensystems.com>
*/
#include <linux/bitfield.h>
#include <linux/bsearch.h>
#include <linux/cacheinfo.h>
#include <linux/debugfs.h>
#include <linux/kvm_host.h>
#include <linux/mm.h>
#include <linux/printk.h>
#include <linux/uaccess.h>
#include <asm/arm_pmuv3.h>
#include <asm/cacheflush.h>
#include <asm/cputype.h>
#include <asm/debug-monitors.h>
#include <asm/esr.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_nested.h>
#include <asm/perf_event.h>
#include <asm/sysreg.h>
#include <trace/events/kvm.h>
#include "sys_regs.h"
#include "vgic/vgic.h"
#include "trace.h"
/*
* For AArch32, we only take care of what is being trapped. Anything
* that has to do with init and userspace access has to go via the
* 64bit interface.
*/
static u64 sys_reg_to_index(const struct sys_reg_desc *reg);
static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 val);
static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
kvm_inject_undefined(vcpu);
return false;
}
static bool bad_trap(struct kvm_vcpu *vcpu,
struct sys_reg_params *params,
const struct sys_reg_desc *r,
const char *msg)
{
WARN_ONCE(1, "Unexpected %s\n", msg);
print_sys_reg_instr(params);
return undef_access(vcpu, params, r);
}
static bool read_from_write_only(struct kvm_vcpu *vcpu,
struct sys_reg_params *params,
const struct sys_reg_desc *r)
{
return bad_trap(vcpu, params, r,
"sys_reg read to write-only register");
}
static bool write_to_read_only(struct kvm_vcpu *vcpu,
struct sys_reg_params *params,
const struct sys_reg_desc *r)
{
return bad_trap(vcpu, params, r,
"sys_reg write to read-only register");
}
#define PURE_EL2_SYSREG(el2) \
case el2: { \
*el1r = el2; \
return true; \
}
#define MAPPED_EL2_SYSREG(el2, el1, fn) \
case el2: { \
*xlate = fn; \
*el1r = el1; \
return true; \
}
static bool get_el2_to_el1_mapping(unsigned int reg,
unsigned int *el1r, u64 (**xlate)(u64))
{
switch (reg) {
PURE_EL2_SYSREG( VPIDR_EL2 );
PURE_EL2_SYSREG( VMPIDR_EL2 );
PURE_EL2_SYSREG( ACTLR_EL2 );
PURE_EL2_SYSREG( HCR_EL2 );
PURE_EL2_SYSREG( MDCR_EL2 );
PURE_EL2_SYSREG( HSTR_EL2 );
PURE_EL2_SYSREG( HACR_EL2 );
PURE_EL2_SYSREG( VTTBR_EL2 );
PURE_EL2_SYSREG( VTCR_EL2 );
PURE_EL2_SYSREG( RVBAR_EL2 );
PURE_EL2_SYSREG( TPIDR_EL2 );
PURE_EL2_SYSREG( HPFAR_EL2 );
PURE_EL2_SYSREG( CNTHCTL_EL2 );
MAPPED_EL2_SYSREG(SCTLR_EL2, SCTLR_EL1,
translate_sctlr_el2_to_sctlr_el1 );
MAPPED_EL2_SYSREG(CPTR_EL2, CPACR_EL1,
translate_cptr_el2_to_cpacr_el1 );
MAPPED_EL2_SYSREG(TTBR0_EL2, TTBR0_EL1,
translate_ttbr0_el2_to_ttbr0_el1 );
MAPPED_EL2_SYSREG(TTBR1_EL2, TTBR1_EL1, NULL );
MAPPED_EL2_SYSREG(TCR_EL2, TCR_EL1,
translate_tcr_el2_to_tcr_el1 );
MAPPED_EL2_SYSREG(VBAR_EL2, VBAR_EL1, NULL );
MAPPED_EL2_SYSREG(AFSR0_EL2, AFSR0_EL1, NULL );
MAPPED_EL2_SYSREG(AFSR1_EL2, AFSR1_EL1, NULL );
MAPPED_EL2_SYSREG(ESR_EL2, ESR_EL1, NULL );
MAPPED_EL2_SYSREG(FAR_EL2, FAR_EL1, NULL );
MAPPED_EL2_SYSREG(MAIR_EL2, MAIR_EL1, NULL );
MAPPED_EL2_SYSREG(AMAIR_EL2, AMAIR_EL1, NULL );
MAPPED_EL2_SYSREG(ELR_EL2, ELR_EL1, NULL );
MAPPED_EL2_SYSREG(SPSR_EL2, SPSR_EL1, NULL );
MAPPED_EL2_SYSREG(ZCR_EL2, ZCR_EL1, NULL );
default:
return false;
}
}
u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
{
u64 val = 0x8badf00d8badf00d;
u64 (*xlate)(u64) = NULL;
unsigned int el1r;
if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
goto memory_read;
if (unlikely(get_el2_to_el1_mapping(reg, &el1r, &xlate))) {
if (!is_hyp_ctxt(vcpu))
goto memory_read;
/*
* If this register does not have an EL1 counterpart,
* then read the stored EL2 version.
*/
if (reg == el1r)
goto memory_read;
/*
* If we have a non-VHE guest and that the sysreg
* requires translation to be used at EL1, use the
* in-memory copy instead.
*/
if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
goto memory_read;
/* Get the current version of the EL1 counterpart. */
WARN_ON(!__vcpu_read_sys_reg_from_cpu(el1r, &val));
return val;
}
/* EL1 register can't be on the CPU if the guest is in vEL2. */
if (unlikely(is_hyp_ctxt(vcpu)))
goto memory_read;
if (__vcpu_read_sys_reg_from_cpu(reg, &val))
return val;
memory_read:
return __vcpu_sys_reg(vcpu, reg);
}
void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
{
u64 (*xlate)(u64) = NULL;
unsigned int el1r;
if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
goto memory_write;
if (unlikely(get_el2_to_el1_mapping(reg, &el1r, &xlate))) {
if (!is_hyp_ctxt(vcpu))
goto memory_write;
/*
* Always store a copy of the write to memory to avoid having
* to reverse-translate virtual EL2 system registers for a
* non-VHE guest hypervisor.
*/
__vcpu_sys_reg(vcpu, reg) = val;
/* No EL1 counterpart? We're done here.? */
if (reg == el1r)
return;
if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
val = xlate(val);
/* Redirect this to the EL1 version of the register. */
WARN_ON(!__vcpu_write_sys_reg_to_cpu(val, el1r));
return;
}
/* EL1 register can't be on the CPU if the guest is in vEL2. */
if (unlikely(is_hyp_ctxt(vcpu)))
goto memory_write;
if (__vcpu_write_sys_reg_to_cpu(val, reg))
return;
memory_write:
__vcpu_sys_reg(vcpu, reg) = val;
}
/* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
#define CSSELR_MAX 14
/*
* Returns the minimum line size for the selected cache, expressed as
* Log2(bytes).
*/
static u8 get_min_cache_line_size(bool icache)
{
u64 ctr = read_sanitised_ftr_reg(SYS_CTR_EL0);
u8 field;
if (icache)
field = SYS_FIELD_GET(CTR_EL0, IminLine, ctr);
else
field = SYS_FIELD_GET(CTR_EL0, DminLine, ctr);
/*
* Cache line size is represented as Log2(words) in CTR_EL0.
* Log2(bytes) can be derived with the following:
*
* Log2(words) + 2 = Log2(bytes / 4) + 2
* = Log2(bytes) - 2 + 2
* = Log2(bytes)
*/
return field + 2;
}
/* Which cache CCSIDR represents depends on CSSELR value. */
static u32 get_ccsidr(struct kvm_vcpu *vcpu, u32 csselr)
{
u8 line_size;
if (vcpu->arch.ccsidr)
return vcpu->arch.ccsidr[csselr];
line_size = get_min_cache_line_size(csselr & CSSELR_EL1_InD);
/*
* Fabricate a CCSIDR value as the overriding value does not exist.
* The real CCSIDR value will not be used as it can vary by the
* physical CPU which the vcpu currently resides in.
*
* The line size is determined with get_min_cache_line_size(), which
* should be valid for all CPUs even if they have different cache
* configuration.
*
* The associativity bits are cleared, meaning the geometry of all data
* and unified caches (which are guaranteed to be PIPT and thus
* non-aliasing) are 1 set and 1 way.
* Guests should not be doing cache operations by set/way at all, and
* for this reason, we trap them and attempt to infer the intent, so
* that we can flush the entire guest's address space at the appropriate
* time. The exposed geometry minimizes the number of the traps.
* [If guests should attempt to infer aliasing properties from the
* geometry (which is not permitted by the architecture), they would
* only do so for virtually indexed caches.]
*
* We don't check if the cache level exists as it is allowed to return
* an UNKNOWN value if not.
*/
return SYS_FIELD_PREP(CCSIDR_EL1, LineSize, line_size - 4);
}
static int set_ccsidr(struct kvm_vcpu *vcpu, u32 csselr, u32 val)
{
u8 line_size = FIELD_GET(CCSIDR_EL1_LineSize, val) + 4;
u32 *ccsidr = vcpu->arch.ccsidr;
u32 i;
if ((val & CCSIDR_EL1_RES0) ||
line_size < get_min_cache_line_size(csselr & CSSELR_EL1_InD))
return -EINVAL;
if (!ccsidr) {
if (val == get_ccsidr(vcpu, csselr))
return 0;
ccsidr = kmalloc_array(CSSELR_MAX, sizeof(u32), GFP_KERNEL_ACCOUNT);
if (!ccsidr)
return -ENOMEM;
for (i = 0; i < CSSELR_MAX; i++)
ccsidr[i] = get_ccsidr(vcpu, i);
vcpu->arch.ccsidr = ccsidr;
}
ccsidr[csselr] = val;
return 0;
}
static bool access_rw(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (p->is_write)
vcpu_write_sys_reg(vcpu, p->regval, r->reg);
else
p->regval = vcpu_read_sys_reg(vcpu, r->reg);
return true;
}
/*
* See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
*/
static bool access_dcsw(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (!p->is_write)
return read_from_write_only(vcpu, p, r);
/*
* Only track S/W ops if we don't have FWB. It still indicates
* that the guest is a bit broken (S/W operations should only
* be done by firmware, knowing that there is only a single
* CPU left in the system, and certainly not from non-secure
* software).
*/
if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
kvm_set_way_flush(vcpu);
return true;
}
static bool access_dcgsw(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (!kvm_has_mte(vcpu->kvm))
return undef_access(vcpu, p, r);
/* Treat MTE S/W ops as we treat the classic ones: with contempt */
return access_dcsw(vcpu, p, r);
}
static void get_access_mask(const struct sys_reg_desc *r, u64 *mask, u64 *shift)
{
switch (r->aarch32_map) {
case AA32_LO:
*mask = GENMASK_ULL(31, 0);
*shift = 0;
break;
case AA32_HI:
*mask = GENMASK_ULL(63, 32);
*shift = 32;
break;
default:
*mask = GENMASK_ULL(63, 0);
*shift = 0;
break;
}
}
/*
* Generic accessor for VM registers. Only called as long as HCR_TVM
* is set. If the guest enables the MMU, we stop trapping the VM
* sys_regs and leave it in complete control of the caches.
*/
static bool access_vm_reg(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
bool was_enabled = vcpu_has_cache_enabled(vcpu);
u64 val, mask, shift;
if (reg_to_encoding(r) == SYS_TCR2_EL1 &&
!kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, TCRX, IMP))
return undef_access(vcpu, p, r);
BUG_ON(!p->is_write);
get_access_mask(r, &mask, &shift);
if (~mask) {
val = vcpu_read_sys_reg(vcpu, r->reg);
val &= ~mask;
} else {
val = 0;
}
val |= (p->regval & (mask >> shift)) << shift;
vcpu_write_sys_reg(vcpu, val, r->reg);
kvm_toggle_cache(vcpu, was_enabled);
return true;
}
static bool access_actlr(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u64 mask, shift;
if (p->is_write)
return ignore_write(vcpu, p);
get_access_mask(r, &mask, &shift);
p->regval = (vcpu_read_sys_reg(vcpu, r->reg) & mask) >> shift;
return true;
}
/*
* Trap handler for the GICv3 SGI generation system register.
* Forward the request to the VGIC emulation.
* The cp15_64 code makes sure this automatically works
* for both AArch64 and AArch32 accesses.
*/
static bool access_gic_sgi(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
bool g1;
if (!kvm_has_gicv3(vcpu->kvm))
return undef_access(vcpu, p, r);
if (!p->is_write)
return read_from_write_only(vcpu, p, r);
/*
* In a system where GICD_CTLR.DS=1, a ICC_SGI0R_EL1 access generates
* Group0 SGIs only, while ICC_SGI1R_EL1 can generate either group,
* depending on the SGI configuration. ICC_ASGI1R_EL1 is effectively
* equivalent to ICC_SGI0R_EL1, as there is no "alternative" secure
* group.
*/
if (p->Op0 == 0) { /* AArch32 */
switch (p->Op1) {
default: /* Keep GCC quiet */
case 0: /* ICC_SGI1R */
g1 = true;
break;
case 1: /* ICC_ASGI1R */
case 2: /* ICC_SGI0R */
g1 = false;
break;
}
} else { /* AArch64 */
switch (p->Op2) {
default: /* Keep GCC quiet */
case 5: /* ICC_SGI1R_EL1 */
g1 = true;
break;
case 6: /* ICC_ASGI1R_EL1 */
case 7: /* ICC_SGI0R_EL1 */
g1 = false;
break;
}
}
vgic_v3_dispatch_sgi(vcpu, p->regval, g1);
return true;
}
static bool access_gic_sre(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (!kvm_has_gicv3(vcpu->kvm))
return undef_access(vcpu, p, r);
if (p->is_write)
return ignore_write(vcpu, p);
p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre;
return true;
}
static bool trap_raz_wi(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (p->is_write)
return ignore_write(vcpu, p);
else
return read_zero(vcpu, p);
}
/*
* ARMv8.1 mandates at least a trivial LORegion implementation, where all the
* RW registers are RES0 (which we can implement as RAZ/WI). On an ARMv8.0
* system, these registers should UNDEF. LORID_EL1 being a RO register, we
* treat it separately.
*/
static bool trap_loregion(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u32 sr = reg_to_encoding(r);
if (!kvm_has_feat(vcpu->kvm, ID_AA64MMFR1_EL1, LO, IMP))
return undef_access(vcpu, p, r);
if (p->is_write && sr == SYS_LORID_EL1)
return write_to_read_only(vcpu, p, r);
return trap_raz_wi(vcpu, p, r);
}
static bool trap_oslar_el1(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u64 oslsr;
if (!p->is_write)
return read_from_write_only(vcpu, p, r);
/* Forward the OSLK bit to OSLSR */
oslsr = __vcpu_sys_reg(vcpu, OSLSR_EL1) & ~OSLSR_EL1_OSLK;
if (p->regval & OSLAR_EL1_OSLK)
oslsr |= OSLSR_EL1_OSLK;
__vcpu_sys_reg(vcpu, OSLSR_EL1) = oslsr;
return true;
}
static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (p->is_write)
return write_to_read_only(vcpu, p, r);
p->regval = __vcpu_sys_reg(vcpu, r->reg);
return true;
}
static int set_oslsr_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 val)
{
/*
* The only modifiable bit is the OSLK bit. Refuse the write if
* userspace attempts to change any other bit in the register.
*/
if ((val ^ rd->val) & ~OSLSR_EL1_OSLK)
return -EINVAL;
__vcpu_sys_reg(vcpu, rd->reg) = val;
return 0;
}
static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (p->is_write) {
return ignore_write(vcpu, p);
} else {
p->regval = read_sysreg(dbgauthstatus_el1);
return true;
}
}
/*
* We want to avoid world-switching all the DBG registers all the
* time:
*
* - If we've touched any debug register, it is likely that we're
* going to touch more of them. It then makes sense to disable the
* traps and start doing the save/restore dance
* - If debug is active (DBG_MDSCR_KDE or DBG_MDSCR_MDE set), it is
* then mandatory to save/restore the registers, as the guest
* depends on them.
*
* For this, we use a DIRTY bit, indicating the guest has modified the
* debug registers, used as follow:
*
* On guest entry:
* - If the dirty bit is set (because we're coming back from trapping),
* disable the traps, save host registers, restore guest registers.
* - If debug is actively in use (DBG_MDSCR_KDE or DBG_MDSCR_MDE set),
* set the dirty bit, disable the traps, save host registers,
* restore guest registers.
* - Otherwise, enable the traps
*
* On guest exit:
* - If the dirty bit is set, save guest registers, restore host
* registers and clear the dirty bit. This ensure that the host can
* now use the debug registers.
*/
static bool trap_debug_regs(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
access_rw(vcpu, p, r);
if (p->is_write)
vcpu_set_flag(vcpu, DEBUG_DIRTY);
trace_trap_reg(__func__, r->reg, p->is_write, p->regval);
return true;
}
/*
* reg_to_dbg/dbg_to_reg
*
* A 32 bit write to a debug register leave top bits alone
* A 32 bit read from a debug register only returns the bottom bits
*
* All writes will set the DEBUG_DIRTY flag to ensure the hyp code
* switches between host and guest values in future.
*/
static void reg_to_dbg(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *rd,
u64 *dbg_reg)
{
u64 mask, shift, val;
get_access_mask(rd, &mask, &shift);
val = *dbg_reg;
val &= ~mask;
val |= (p->regval & (mask >> shift)) << shift;
*dbg_reg = val;
vcpu_set_flag(vcpu, DEBUG_DIRTY);
}
static void dbg_to_reg(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *rd,
u64 *dbg_reg)
{
u64 mask, shift;
get_access_mask(rd, &mask, &shift);
p->regval = (*dbg_reg & mask) >> shift;
}
static bool trap_bvr(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *rd)
{
u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm];
if (p->is_write)
reg_to_dbg(vcpu, p, rd, dbg_reg);
else
dbg_to_reg(vcpu, p, rd, dbg_reg);
trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg);
return true;
}
static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 val)
{
vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm] = val;
return 0;
}
static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 *val)
{
*val = vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm];
return 0;
}
static u64 reset_bvr(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm] = rd->val;
return rd->val;
}
static bool trap_bcr(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *rd)
{
u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm];
if (p->is_write)
reg_to_dbg(vcpu, p, rd, dbg_reg);
else
dbg_to_reg(vcpu, p, rd, dbg_reg);
trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg);
return true;
}
static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 val)
{
vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm] = val;
return 0;
}
static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 *val)
{
*val = vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm];
return 0;
}
static u64 reset_bcr(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm] = rd->val;
return rd->val;
}
static bool trap_wvr(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *rd)
{
u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm];
if (p->is_write)
reg_to_dbg(vcpu, p, rd, dbg_reg);
else
dbg_to_reg(vcpu, p, rd, dbg_reg);
trace_trap_reg(__func__, rd->CRm, p->is_write,
vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]);
return true;
}
static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 val)
{
vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm] = val;
return 0;
}
static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 *val)
{
*val = vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm];
return 0;
}
static u64 reset_wvr(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm] = rd->val;
return rd->val;
}
static bool trap_wcr(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *rd)
{
u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm];
if (p->is_write)
reg_to_dbg(vcpu, p, rd, dbg_reg);
else
dbg_to_reg(vcpu, p, rd, dbg_reg);
trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg);
return true;
}
static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 val)
{
vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm] = val;
return 0;
}
static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 *val)
{
*val = vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm];
return 0;
}
static u64 reset_wcr(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm] = rd->val;
return rd->val;
}
static u64 reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
u64 amair = read_sysreg(amair_el1);
vcpu_write_sys_reg(vcpu, amair, AMAIR_EL1);
return amair;
}
static u64 reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
u64 actlr = read_sysreg(actlr_el1);
vcpu_write_sys_reg(vcpu, actlr, ACTLR_EL1);
return actlr;
}
static u64 reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
u64 mpidr;
/*
* Map the vcpu_id into the first three affinity level fields of
* the MPIDR. We limit the number of VCPUs in level 0 due to a
* limitation to 16 CPUs in that level in the ICC_SGIxR registers
* of the GICv3 to be able to address each CPU directly when
* sending IPIs.
*/
mpidr = (vcpu->vcpu_id & 0x0f) << MPIDR_LEVEL_SHIFT(0);
mpidr |= ((vcpu->vcpu_id >> 4) & 0xff) << MPIDR_LEVEL_SHIFT(1);
mpidr |= ((vcpu->vcpu_id >> 12) & 0xff) << MPIDR_LEVEL_SHIFT(2);
mpidr |= (1ULL << 31);
vcpu_write_sys_reg(vcpu, mpidr, MPIDR_EL1);
return mpidr;
}
static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *r)
{
if (kvm_vcpu_has_pmu(vcpu))
return 0;
return REG_HIDDEN;
}
static u64 reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
u64 mask = BIT(ARMV8_PMU_CYCLE_IDX);
u8 n = vcpu->kvm->arch.pmcr_n;
if (n)
mask |= GENMASK(n - 1, 0);
reset_unknown(vcpu, r);
__vcpu_sys_reg(vcpu, r->reg) &= mask;
return __vcpu_sys_reg(vcpu, r->reg);
}
static u64 reset_pmevcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
reset_unknown(vcpu, r);
__vcpu_sys_reg(vcpu, r->reg) &= GENMASK(31, 0);
return __vcpu_sys_reg(vcpu, r->reg);
}
static u64 reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
/* This thing will UNDEF, who cares about the reset value? */
if (!kvm_vcpu_has_pmu(vcpu))
return 0;
reset_unknown(vcpu, r);
__vcpu_sys_reg(vcpu, r->reg) &= kvm_pmu_evtyper_mask(vcpu->kvm);
return __vcpu_sys_reg(vcpu, r->reg);
}
static u64 reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
reset_unknown(vcpu, r);
__vcpu_sys_reg(vcpu, r->reg) &= PMSELR_EL0_SEL_MASK;
return __vcpu_sys_reg(vcpu, r->reg);
}
static u64 reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
u64 pmcr = 0;
if (!kvm_supports_32bit_el0())
pmcr |= ARMV8_PMU_PMCR_LC;
/*
* The value of PMCR.N field is included when the
* vCPU register is read via kvm_vcpu_read_pmcr().
*/
__vcpu_sys_reg(vcpu, r->reg) = pmcr;
return __vcpu_sys_reg(vcpu, r->reg);
}
static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags)
{
u64 reg = __vcpu_sys_reg(vcpu, PMUSERENR_EL0);
bool enabled = (reg & flags) || vcpu_mode_priv(vcpu);
if (!enabled)
kvm_inject_undefined(vcpu);
return !enabled;
}
static bool pmu_access_el0_disabled(struct kvm_vcpu *vcpu)
{
return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_EN);
}
static bool pmu_write_swinc_el0_disabled(struct kvm_vcpu *vcpu)
{
return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_SW | ARMV8_PMU_USERENR_EN);
}
static bool pmu_access_cycle_counter_el0_disabled(struct kvm_vcpu *vcpu)
{
return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_EN);
}
static bool pmu_access_event_counter_el0_disabled(struct kvm_vcpu *vcpu)
{
return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_EN);
}
static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u64 val;
if (pmu_access_el0_disabled(vcpu))
return false;
if (p->is_write) {
/*
* Only update writeable bits of PMCR (continuing into
* kvm_pmu_handle_pmcr() as well)
*/
val = kvm_vcpu_read_pmcr(vcpu);
val &= ~ARMV8_PMU_PMCR_MASK;
val |= p->regval & ARMV8_PMU_PMCR_MASK;
if (!kvm_supports_32bit_el0())
val |= ARMV8_PMU_PMCR_LC;
kvm_pmu_handle_pmcr(vcpu, val);
} else {
/* PMCR.P & PMCR.C are RAZ */
val = kvm_vcpu_read_pmcr(vcpu)
& ~(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C);
p->regval = val;
}
return true;
}
static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (pmu_access_event_counter_el0_disabled(vcpu))
return false;
if (p->is_write)
__vcpu_sys_reg(vcpu, PMSELR_EL0) = p->regval;
else
/* return PMSELR.SEL field */
p->regval = __vcpu_sys_reg(vcpu, PMSELR_EL0)
& PMSELR_EL0_SEL_MASK;
return true;
}
static bool access_pmceid(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u64 pmceid, mask, shift;
BUG_ON(p->is_write);
if (pmu_access_el0_disabled(vcpu))
return false;
get_access_mask(r, &mask, &shift);
pmceid = kvm_pmu_get_pmceid(vcpu, (p->Op2 & 1));
pmceid &= mask;
pmceid >>= shift;
p->regval = pmceid;
return true;
}
static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx)
{
u64 pmcr, val;
pmcr = kvm_vcpu_read_pmcr(vcpu);
val = FIELD_GET(ARMV8_PMU_PMCR_N, pmcr);
if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) {
kvm_inject_undefined(vcpu);
return false;
}
return true;
}
static int get_pmu_evcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
u64 *val)
{
u64 idx;
if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 0)
/* PMCCNTR_EL0 */
idx = ARMV8_PMU_CYCLE_IDX;
else
/* PMEVCNTRn_EL0 */
idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
*val = kvm_pmu_get_counter_value(vcpu, idx);
return 0;
}
static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u64 idx = ~0UL;
if (r->CRn == 9 && r->CRm == 13) {
if (r->Op2 == 2) {
/* PMXEVCNTR_EL0 */
if (pmu_access_event_counter_el0_disabled(vcpu))
return false;
idx = SYS_FIELD_GET(PMSELR_EL0, SEL,
__vcpu_sys_reg(vcpu, PMSELR_EL0));
} else if (r->Op2 == 0) {
/* PMCCNTR_EL0 */
if (pmu_access_cycle_counter_el0_disabled(vcpu))
return false;
idx = ARMV8_PMU_CYCLE_IDX;
}
} else if (r->CRn == 0 && r->CRm == 9) {
/* PMCCNTR */
if (pmu_access_event_counter_el0_disabled(vcpu))
return false;
idx = ARMV8_PMU_CYCLE_IDX;
} else if (r->CRn == 14 && (r->CRm & 12) == 8) {
/* PMEVCNTRn_EL0 */
if (pmu_access_event_counter_el0_disabled(vcpu))
return false;
idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
}
/* Catch any decoding mistake */
WARN_ON(idx == ~0UL);
if (!pmu_counter_idx_valid(vcpu, idx))
return false;
if (p->is_write) {
if (pmu_access_el0_disabled(vcpu))
return false;
kvm_pmu_set_counter_value(vcpu, idx, p->regval);
} else {
p->regval = kvm_pmu_get_counter_value(vcpu, idx);
}
return true;
}
static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u64 idx, reg;
if (pmu_access_el0_disabled(vcpu))
return false;
if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 1) {
/* PMXEVTYPER_EL0 */
idx = SYS_FIELD_GET(PMSELR_EL0, SEL, __vcpu_sys_reg(vcpu, PMSELR_EL0));
reg = PMEVTYPER0_EL0 + idx;
} else if (r->CRn == 14 && (r->CRm & 12) == 12) {
idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
if (idx == ARMV8_PMU_CYCLE_IDX)
reg = PMCCFILTR_EL0;
else
/* PMEVTYPERn_EL0 */
reg = PMEVTYPER0_EL0 + idx;
} else {
BUG();
}
if (!pmu_counter_idx_valid(vcpu, idx))
return false;
if (p->is_write) {
kvm_pmu_set_counter_event_type(vcpu, p->regval, idx);
kvm_vcpu_pmu_restore_guest(vcpu);
} else {
p->regval = __vcpu_sys_reg(vcpu, reg);
}
return true;
}
static int set_pmreg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val)
{
bool set;
val &= kvm_pmu_valid_counter_mask(vcpu);
switch (r->reg) {
case PMOVSSET_EL0:
/* CRm[1] being set indicates a SET register, and CLR otherwise */
set = r->CRm & 2;
break;
default:
/* Op2[0] being set indicates a SET register, and CLR otherwise */
set = r->Op2 & 1;
break;
}
if (set)
__vcpu_sys_reg(vcpu, r->reg) |= val;
else
__vcpu_sys_reg(vcpu, r->reg) &= ~val;
return 0;
}
static int get_pmreg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val)
{
u64 mask = kvm_pmu_valid_counter_mask(vcpu);
*val = __vcpu_sys_reg(vcpu, r->reg) & mask;
return 0;
}
static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u64 val, mask;
if (pmu_access_el0_disabled(vcpu))
return false;
mask = kvm_pmu_valid_counter_mask(vcpu);
if (p->is_write) {
val = p->regval & mask;
if (r->Op2 & 0x1) {
/* accessing PMCNTENSET_EL0 */
__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val;
kvm_pmu_enable_counter_mask(vcpu, val);
kvm_vcpu_pmu_restore_guest(vcpu);
} else {
/* accessing PMCNTENCLR_EL0 */
__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val;
kvm_pmu_disable_counter_mask(vcpu, val);
}
} else {
p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
}
return true;
}
static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u64 mask = kvm_pmu_valid_counter_mask(vcpu);
if (check_pmu_access_disabled(vcpu, 0))
return false;
if (p->is_write) {
u64 val = p->regval & mask;
if (r->Op2 & 0x1)
/* accessing PMINTENSET_EL1 */
__vcpu_sys_reg(vcpu, PMINTENSET_EL1) |= val;
else
/* accessing PMINTENCLR_EL1 */
__vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= ~val;
} else {
p->regval = __vcpu_sys_reg(vcpu, PMINTENSET_EL1);
}
return true;
}
static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u64 mask = kvm_pmu_valid_counter_mask(vcpu);
if (pmu_access_el0_disabled(vcpu))
return false;
if (p->is_write) {
if (r->CRm & 0x2)
/* accessing PMOVSSET_EL0 */
__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= (p->regval & mask);
else
/* accessing PMOVSCLR_EL0 */
__vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask);
} else {
p->regval = __vcpu_sys_reg(vcpu, PMOVSSET_EL0);
}
return true;
}
static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u64 mask;
if (!p->is_write)
return read_from_write_only(vcpu, p, r);
if (pmu_write_swinc_el0_disabled(vcpu))
return false;
mask = kvm_pmu_valid_counter_mask(vcpu);
kvm_pmu_software_increment(vcpu, p->regval & mask);
return true;
}
static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (p->is_write) {
if (!vcpu_mode_priv(vcpu))
return undef_access(vcpu, p, r);
__vcpu_sys_reg(vcpu, PMUSERENR_EL0) =
p->regval & ARMV8_PMU_USERENR_MASK;
} else {
p->regval = __vcpu_sys_reg(vcpu, PMUSERENR_EL0)
& ARMV8_PMU_USERENR_MASK;
}
return true;
}
static int get_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
u64 *val)
{
*val = kvm_vcpu_read_pmcr(vcpu);
return 0;
}
static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
u64 val)
{
u8 new_n = FIELD_GET(ARMV8_PMU_PMCR_N, val);
struct kvm *kvm = vcpu->kvm;
mutex_lock(&kvm->arch.config_lock);
/*
* The vCPU can't have more counters than the PMU hardware
* implements. Ignore this error to maintain compatibility
* with the existing KVM behavior.
*/
if (!kvm_vm_has_ran_once(kvm) &&
new_n <= kvm_arm_pmu_get_max_counters(kvm))
kvm->arch.pmcr_n = new_n;
mutex_unlock(&kvm->arch.config_lock);
/*
* Ignore writes to RES0 bits, read only bits that are cleared on
* vCPU reset, and writable bits that KVM doesn't support yet.
* (i.e. only PMCR.N and bits [7:0] are mutable from userspace)
* The LP bit is RES0 when FEAT_PMUv3p5 is not supported on the vCPU.
* But, we leave the bit as it is here, as the vCPU's PMUver might
* be changed later (NOTE: the bit will be cleared on first vCPU run
* if necessary).
*/
val &= ARMV8_PMU_PMCR_MASK;
/* The LC bit is RES1 when AArch32 is not supported */
if (!kvm_supports_32bit_el0())
val |= ARMV8_PMU_PMCR_LC;
__vcpu_sys_reg(vcpu, r->reg) = val;
return 0;
}
/* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
#define DBG_BCR_BVR_WCR_WVR_EL1(n) \
{ SYS_DESC(SYS_DBGBVRn_EL1(n)), \
trap_bvr, reset_bvr, 0, 0, get_bvr, set_bvr }, \
{ SYS_DESC(SYS_DBGBCRn_EL1(n)), \
trap_bcr, reset_bcr, 0, 0, get_bcr, set_bcr }, \
{ SYS_DESC(SYS_DBGWVRn_EL1(n)), \
trap_wvr, reset_wvr, 0, 0, get_wvr, set_wvr }, \
{ SYS_DESC(SYS_DBGWCRn_EL1(n)), \
trap_wcr, reset_wcr, 0, 0, get_wcr, set_wcr }
#define PMU_SYS_REG(name) \
SYS_DESC(SYS_##name), .reset = reset_pmu_reg, \
.visibility = pmu_visibility
/* Macro to expand the PMEVCNTRn_EL0 register */
#define PMU_PMEVCNTR_EL0(n) \
{ PMU_SYS_REG(PMEVCNTRn_EL0(n)), \
.reset = reset_pmevcntr, .get_user = get_pmu_evcntr, \
.access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), }
/* Macro to expand the PMEVTYPERn_EL0 register */
#define PMU_PMEVTYPER_EL0(n) \
{ PMU_SYS_REG(PMEVTYPERn_EL0(n)), \
.reset = reset_pmevtyper, \
.access = access_pmu_evtyper, .reg = (PMEVTYPER0_EL0 + n), }
/* Macro to expand the AMU counter and type registers*/
#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), undef_access }
#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), undef_access }
#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), undef_access }
#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), undef_access }
static unsigned int ptrauth_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN;
}
/*
* If we land here on a PtrAuth access, that is because we didn't
* fixup the access on exit by allowing the PtrAuth sysregs. The only
* way this happens is when the guest does not have PtrAuth support
* enabled.
*/
#define __PTRAUTH_KEY(k) \
{ SYS_DESC(SYS_## k), undef_access, reset_unknown, k, \
.visibility = ptrauth_visibility}
#define PTRAUTH_KEY(k) \
__PTRAUTH_KEY(k ## KEYLO_EL1), \
__PTRAUTH_KEY(k ## KEYHI_EL1)
static bool access_arch_timer(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
enum kvm_arch_timers tmr;
enum kvm_arch_timer_regs treg;
u64 reg = reg_to_encoding(r);
switch (reg) {
case SYS_CNTP_TVAL_EL0:
case SYS_AARCH32_CNTP_TVAL:
tmr = TIMER_PTIMER;
treg = TIMER_REG_TVAL;
break;
case SYS_CNTP_CTL_EL0:
case SYS_AARCH32_CNTP_CTL:
tmr = TIMER_PTIMER;
treg = TIMER_REG_CTL;
break;
case SYS_CNTP_CVAL_EL0:
case SYS_AARCH32_CNTP_CVAL:
tmr = TIMER_PTIMER;
treg = TIMER_REG_CVAL;
break;
case SYS_CNTPCT_EL0:
case SYS_CNTPCTSS_EL0:
case SYS_AARCH32_CNTPCT:
tmr = TIMER_PTIMER;
treg = TIMER_REG_CNT;
break;
default:
print_sys_reg_msg(p, "%s", "Unhandled trapped timer register");
return undef_access(vcpu, p, r);
}
if (p->is_write)
kvm_arm_timer_write_sysreg(vcpu, tmr, treg, p->regval);
else
p->regval = kvm_arm_timer_read_sysreg(vcpu, tmr, treg);
return true;
}
static s64 kvm_arm64_ftr_safe_value(u32 id, const struct arm64_ftr_bits *ftrp,
s64 new, s64 cur)
{
struct arm64_ftr_bits kvm_ftr = *ftrp;
/* Some features have different safe value type in KVM than host features */
switch (id) {
case SYS_ID_AA64DFR0_EL1:
switch (kvm_ftr.shift) {
case ID_AA64DFR0_EL1_PMUVer_SHIFT:
kvm_ftr.type = FTR_LOWER_SAFE;
break;
case ID_AA64DFR0_EL1_DebugVer_SHIFT:
kvm_ftr.type = FTR_LOWER_SAFE;
break;
}
break;
case SYS_ID_DFR0_EL1:
if (kvm_ftr.shift == ID_DFR0_EL1_PerfMon_SHIFT)
kvm_ftr.type = FTR_LOWER_SAFE;
break;
}
return arm64_ftr_safe_value(&kvm_ftr, new, cur);
}
/*
* arm64_check_features() - Check if a feature register value constitutes
* a subset of features indicated by the idreg's KVM sanitised limit.
*
* This function will check if each feature field of @val is the "safe" value
* against idreg's KVM sanitised limit return from reset() callback.
* If a field value in @val is the same as the one in limit, it is always
* considered the safe value regardless For register fields that are not in
* writable, only the value in limit is considered the safe value.
*
* Return: 0 if all the fields are safe. Otherwise, return negative errno.
*/
static int arm64_check_features(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd,
u64 val)
{
const struct arm64_ftr_reg *ftr_reg;
const struct arm64_ftr_bits *ftrp = NULL;
u32 id = reg_to_encoding(rd);
u64 writable_mask = rd->val;
u64 limit = rd->reset(vcpu, rd);
u64 mask = 0;
/*
* Hidden and unallocated ID registers may not have a corresponding
* struct arm64_ftr_reg. Of course, if the register is RAZ we know the
* only safe value is 0.
*/
if (sysreg_visible_as_raz(vcpu, rd))
return val ? -E2BIG : 0;
ftr_reg = get_arm64_ftr_reg(id);
if (!ftr_reg)
return -EINVAL;
ftrp = ftr_reg->ftr_bits;
for (; ftrp && ftrp->width; ftrp++) {
s64 f_val, f_lim, safe_val;
u64 ftr_mask;
ftr_mask = arm64_ftr_mask(ftrp);
if ((ftr_mask & writable_mask) != ftr_mask)
continue;
f_val = arm64_ftr_value(ftrp, val);
f_lim = arm64_ftr_value(ftrp, limit);
mask |= ftr_mask;
if (f_val == f_lim)
safe_val = f_val;
else
safe_val = kvm_arm64_ftr_safe_value(id, ftrp, f_val, f_lim);
if (safe_val != f_val)
return -E2BIG;
}
/* For fields that are not writable, values in limit are the safe values. */
if ((val & ~mask) != (limit & ~mask))
return -E2BIG;
return 0;
}
static u8 pmuver_to_perfmon(u8 pmuver)
{
switch (pmuver) {
case ID_AA64DFR0_EL1_PMUVer_IMP:
return ID_DFR0_EL1_PerfMon_PMUv3;
case ID_AA64DFR0_EL1_PMUVer_IMP_DEF:
return ID_DFR0_EL1_PerfMon_IMPDEF;
default:
/* Anything ARMv8.1+ and NI have the same value. For now. */
return pmuver;
}
}
/* Read a sanitised cpufeature ID register by sys_reg_desc */
static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *r)
{
u32 id = reg_to_encoding(r);
u64 val;
if (sysreg_visible_as_raz(vcpu, r))
return 0;
val = read_sanitised_ftr_reg(id);
switch (id) {
case SYS_ID_AA64PFR1_EL1:
if (!kvm_has_mte(vcpu->kvm))
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SME);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_RNDR_trap);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_NMI);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_GCS);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_THE);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTEX);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_DF2);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_PFAR);
break;
case SYS_ID_AA64PFR2_EL1:
/* We only expose FPMR */
val &= ID_AA64PFR2_EL1_FPMR;
break;
case SYS_ID_AA64ISAR1_EL1:
if (!vcpu_has_ptrauth(vcpu))
val &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA) |
ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API) |
ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPA) |
ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPI));
break;
case SYS_ID_AA64ISAR2_EL1:
if (!vcpu_has_ptrauth(vcpu))
val &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3) |
ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3));
if (!cpus_have_final_cap(ARM64_HAS_WFXT))
val &= ~ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_WFxT);
break;
case SYS_ID_AA64MMFR2_EL1:
val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK;
break;
case SYS_ID_AA64MMFR3_EL1:
val &= ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_S1POE;
break;
case SYS_ID_MMFR4_EL1:
val &= ~ARM64_FEATURE_MASK(ID_MMFR4_EL1_CCIDX);
break;
}
return val;
}
static u64 kvm_read_sanitised_id_reg(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *r)
{
return __kvm_read_sanitised_id_reg(vcpu, r);
}
static u64 read_id_reg(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
return kvm_read_vm_id_reg(vcpu->kvm, reg_to_encoding(r));
}
static bool is_feature_id_reg(u32 encoding)
{
return (sys_reg_Op0(encoding) == 3 &&
(sys_reg_Op1(encoding) < 2 || sys_reg_Op1(encoding) == 3) &&
sys_reg_CRn(encoding) == 0 &&
sys_reg_CRm(encoding) <= 7);
}
/*
* Return true if the register's (Op0, Op1, CRn, CRm, Op2) is
* (3, 0, 0, crm, op2), where 1<=crm<8, 0<=op2<8, which is the range of ID
* registers KVM maintains on a per-VM basis.
*/
static inline bool is_vm_ftr_id_reg(u32 id)
{
if (id == SYS_CTR_EL0)
return true;
return (sys_reg_Op0(id) == 3 && sys_reg_Op1(id) == 0 &&
sys_reg_CRn(id) == 0 && sys_reg_CRm(id) >= 1 &&
sys_reg_CRm(id) < 8);
}
static inline bool is_vcpu_ftr_id_reg(u32 id)
{
return is_feature_id_reg(id) && !is_vm_ftr_id_reg(id);
}
static inline bool is_aa32_id_reg(u32 id)
{
return (sys_reg_Op0(id) == 3 && sys_reg_Op1(id) == 0 &&
sys_reg_CRn(id) == 0 && sys_reg_CRm(id) >= 1 &&
sys_reg_CRm(id) <= 3);
}
static unsigned int id_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *r)
{
u32 id = reg_to_encoding(r);
switch (id) {
case SYS_ID_AA64ZFR0_EL1:
if (!vcpu_has_sve(vcpu))
return REG_RAZ;
break;
}
return 0;
}
static unsigned int aa32_id_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *r)
{
/*
* AArch32 ID registers are UNKNOWN if AArch32 isn't implemented at any
* EL. Promote to RAZ/WI in order to guarantee consistency between
* systems.
*/
if (!kvm_supports_32bit_el0())
return REG_RAZ | REG_USER_WI;
return id_visibility(vcpu, r);
}
static unsigned int raz_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *r)
{
return REG_RAZ;
}
/* cpufeature ID register access trap handlers */
static bool access_id_reg(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (p->is_write)
return write_to_read_only(vcpu, p, r);
p->regval = read_id_reg(vcpu, r);
return true;
}
/* Visibility overrides for SVE-specific control registers */
static unsigned int sve_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
if (vcpu_has_sve(vcpu))
return 0;
return REG_HIDDEN;
}
static unsigned int sme_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SME, IMP))
return 0;
return REG_HIDDEN;
}
static unsigned int fp8_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
if (kvm_has_fpmr(vcpu->kvm))
return 0;
return REG_HIDDEN;
}
static u64 read_sanitised_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
u64 val = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
if (!vcpu_has_sve(vcpu))
val &= ~ID_AA64PFR0_EL1_SVE_MASK;
/*
* The default is to expose CSV2 == 1 if the HW isn't affected.
* Although this is a per-CPU feature, we make it global because
* asymmetric systems are just a nuisance.
*
* Userspace can override this as long as it doesn't promise
* the impossible.
*/
if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED) {
val &= ~ID_AA64PFR0_EL1_CSV2_MASK;
val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, CSV2, IMP);
}
if (arm64_get_meltdown_state() == SPECTRE_UNAFFECTED) {
val &= ~ID_AA64PFR0_EL1_CSV3_MASK;
val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, CSV3, IMP);
}
if (kvm_vgic_global_state.type == VGIC_V3) {
val &= ~ID_AA64PFR0_EL1_GIC_MASK;
val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP);
}
val &= ~ID_AA64PFR0_EL1_AMU_MASK;
return val;
}
#define ID_REG_LIMIT_FIELD_ENUM(val, reg, field, limit) \
({ \
u64 __f_val = FIELD_GET(reg##_##field##_MASK, val); \
(val) &= ~reg##_##field##_MASK; \
(val) |= FIELD_PREP(reg##_##field##_MASK, \
min(__f_val, \
(u64)SYS_FIELD_VALUE(reg, field, limit))); \
(val); \
})
static u64 read_sanitised_id_aa64dfr0_el1(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
u64 val = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64DFR0_EL1, DebugVer, V8P8);
/*
* Only initialize the PMU version if the vCPU was configured with one.
*/
val &= ~ID_AA64DFR0_EL1_PMUVer_MASK;
if (kvm_vcpu_has_pmu(vcpu))
val |= SYS_FIELD_PREP(ID_AA64DFR0_EL1, PMUVer,
kvm_arm_pmu_get_pmuver_limit());
/* Hide SPE from guests */
val &= ~ID_AA64DFR0_EL1_PMSVer_MASK;
return val;
}
static int set_id_aa64dfr0_el1(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd,
u64 val)
{
u8 debugver = SYS_FIELD_GET(ID_AA64DFR0_EL1, DebugVer, val);
u8 pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer, val);
/*
* Prior to commit 3d0dba5764b9 ("KVM: arm64: PMU: Move the
* ID_AA64DFR0_EL1.PMUver limit to VM creation"), KVM erroneously
* exposed an IMP_DEF PMU to userspace and the guest on systems w/
* non-architectural PMUs. Of course, PMUv3 is the only game in town for
* PMU virtualization, so the IMP_DEF value was rather user-hostile.
*
* At minimum, we're on the hook to allow values that were given to
* userspace by KVM. Cover our tracks here and replace the IMP_DEF value
* with a more sensible NI. The value of an ID register changing under
* the nose of the guest is unfortunate, but is certainly no more
* surprising than an ill-guided PMU driver poking at impdef system
* registers that end in an UNDEF...
*/
if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
val &= ~ID_AA64DFR0_EL1_PMUVer_MASK;
/*
* ID_AA64DFR0_EL1.DebugVer is one of those awkward fields with a
* nonzero minimum safe value.
*/
if (debugver < ID_AA64DFR0_EL1_DebugVer_IMP)
return -EINVAL;
return set_id_reg(vcpu, rd, val);
}
static u64 read_sanitised_id_dfr0_el1(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
u8 perfmon = pmuver_to_perfmon(kvm_arm_pmu_get_pmuver_limit());
u64 val = read_sanitised_ftr_reg(SYS_ID_DFR0_EL1);
val &= ~ID_DFR0_EL1_PerfMon_MASK;
if (kvm_vcpu_has_pmu(vcpu))
val |= SYS_FIELD_PREP(ID_DFR0_EL1, PerfMon, perfmon);
val = ID_REG_LIMIT_FIELD_ENUM(val, ID_DFR0_EL1, CopDbg, Debugv8p8);
return val;
}
static int set_id_dfr0_el1(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd,
u64 val)
{
u8 perfmon = SYS_FIELD_GET(ID_DFR0_EL1, PerfMon, val);
u8 copdbg = SYS_FIELD_GET(ID_DFR0_EL1, CopDbg, val);
if (perfmon == ID_DFR0_EL1_PerfMon_IMPDEF) {
val &= ~ID_DFR0_EL1_PerfMon_MASK;
perfmon = 0;
}
/*
* Allow DFR0_EL1.PerfMon to be set from userspace as long as
* it doesn't promise more than what the HW gives us on the
* AArch64 side (as everything is emulated with that), and
* that this is a PMUv3.
*/
if (perfmon != 0 && perfmon < ID_DFR0_EL1_PerfMon_PMUv3)
return -EINVAL;
if (copdbg < ID_DFR0_EL1_CopDbg_Armv8)
return -EINVAL;
return set_id_reg(vcpu, rd, val);
}
/*
* cpufeature ID register user accessors
*
* For now, these registers are immutable for userspace, so no values
* are stored, and for set_id_reg() we don't allow the effective value
* to be changed.
*/
static int get_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 *val)
{
/*
* Avoid locking if the VM has already started, as the ID registers are
* guaranteed to be invariant at that point.
*/
if (kvm_vm_has_ran_once(vcpu->kvm)) {
*val = read_id_reg(vcpu, rd);
return 0;
}
mutex_lock(&vcpu->kvm->arch.config_lock);
*val = read_id_reg(vcpu, rd);
mutex_unlock(&vcpu->kvm->arch.config_lock);
return 0;
}
static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 val)
{
u32 id = reg_to_encoding(rd);
int ret;
mutex_lock(&vcpu->kvm->arch.config_lock);
/*
* Once the VM has started the ID registers are immutable. Reject any
* write that does not match the final register value.
*/
if (kvm_vm_has_ran_once(vcpu->kvm)) {
if (val != read_id_reg(vcpu, rd))
ret = -EBUSY;
else
ret = 0;
mutex_unlock(&vcpu->kvm->arch.config_lock);
return ret;
}
ret = arm64_check_features(vcpu, rd, val);
if (!ret)
kvm_set_vm_id_reg(vcpu->kvm, id, val);
mutex_unlock(&vcpu->kvm->arch.config_lock);
/*
* arm64_check_features() returns -E2BIG to indicate the register's
* feature set is a superset of the maximally-allowed register value.
* While it would be nice to precisely describe this to userspace, the
* existing UAPI for KVM_SET_ONE_REG has it that invalid register
* writes return -EINVAL.
*/
if (ret == -E2BIG)
ret = -EINVAL;
return ret;
}
void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val)
{
u64 *p = __vm_id_reg(&kvm->arch, reg);
lockdep_assert_held(&kvm->arch.config_lock);
if (KVM_BUG_ON(kvm_vm_has_ran_once(kvm) || !p, kvm))
return;
*p = val;
}
static int get_raz_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 *val)
{
*val = 0;
return 0;
}
static int set_wi_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 val)
{
return 0;
}
static bool access_ctr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (p->is_write)
return write_to_read_only(vcpu, p, r);
p->regval = kvm_read_vm_id_reg(vcpu->kvm, SYS_CTR_EL0);
return true;
}
static bool access_clidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (p->is_write)
return write_to_read_only(vcpu, p, r);
p->regval = __vcpu_sys_reg(vcpu, r->reg);
return true;
}
/*
* Fabricate a CLIDR_EL1 value instead of using the real value, which can vary
* by the physical CPU which the vcpu currently resides in.
*/
static u64 reset_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
u64 ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0);
u64 clidr;
u8 loc;
if ((ctr_el0 & CTR_EL0_IDC)) {
/*
* Data cache clean to the PoU is not required so LoUU and LoUIS
* will not be set and a unified cache, which will be marked as
* LoC, will be added.
*
* If not DIC, let the unified cache L2 so that an instruction
* cache can be added as L1 later.
*/
loc = (ctr_el0 & CTR_EL0_DIC) ? 1 : 2;
clidr = CACHE_TYPE_UNIFIED << CLIDR_CTYPE_SHIFT(loc);
} else {
/*
* Data cache clean to the PoU is required so let L1 have a data
* cache and mark it as LoUU and LoUIS. As L1 has a data cache,
* it can be marked as LoC too.
*/
loc = 1;
clidr = 1 << CLIDR_LOUU_SHIFT;
clidr |= 1 << CLIDR_LOUIS_SHIFT;
clidr |= CACHE_TYPE_DATA << CLIDR_CTYPE_SHIFT(1);
}
/*
* Instruction cache invalidation to the PoU is required so let L1 have
* an instruction cache. If L1 already has a data cache, it will be
* CACHE_TYPE_SEPARATE.
*/
if (!(ctr_el0 & CTR_EL0_DIC))
clidr |= CACHE_TYPE_INST << CLIDR_CTYPE_SHIFT(1);
clidr |= loc << CLIDR_LOC_SHIFT;
/*
* Add tag cache unified to data cache. Allocation tags and data are
* unified in a cache line so that it looks valid even if there is only
* one cache line.
*/
if (kvm_has_mte(vcpu->kvm))
clidr |= 2 << CLIDR_TTYPE_SHIFT(loc);
__vcpu_sys_reg(vcpu, r->reg) = clidr;
return __vcpu_sys_reg(vcpu, r->reg);
}
static int set_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
u64 val)
{
u64 ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0);
u64 idc = !CLIDR_LOC(val) || (!CLIDR_LOUIS(val) && !CLIDR_LOUU(val));
if ((val & CLIDR_EL1_RES0) || (!(ctr_el0 & CTR_EL0_IDC) && idc))
return -EINVAL;
__vcpu_sys_reg(vcpu, rd->reg) = val;
return 0;
}
static bool access_csselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
int reg = r->reg;
if (p->is_write)
vcpu_write_sys_reg(vcpu, p->regval, reg);
else
p->regval = vcpu_read_sys_reg(vcpu, reg);
return true;
}
static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u32 csselr;
if (p->is_write)
return write_to_read_only(vcpu, p, r);
csselr = vcpu_read_sys_reg(vcpu, CSSELR_EL1);
csselr &= CSSELR_EL1_Level | CSSELR_EL1_InD;
if (csselr < CSSELR_MAX)
p->regval = get_ccsidr(vcpu, csselr);
return true;
}
static unsigned int mte_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
if (kvm_has_mte(vcpu->kvm))
return 0;
return REG_HIDDEN;
}
#define MTE_REG(name) { \
SYS_DESC(SYS_##name), \
.access = undef_access, \
.reset = reset_unknown, \
.reg = name, \
.visibility = mte_visibility, \
}
static unsigned int el2_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
if (vcpu_has_nv(vcpu))
return 0;
return REG_HIDDEN;
}
static bool bad_vncr_trap(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
/*
* We really shouldn't be here, and this is likely the result
* of a misconfigured trap, as this register should target the
* VNCR page, and nothing else.
*/
return bad_trap(vcpu, p, r,
"trap of VNCR-backed register");
}
static bool bad_redir_trap(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
/*
* We really shouldn't be here, and this is likely the result
* of a misconfigured trap, as this register should target the
* corresponding EL1, and nothing else.
*/
return bad_trap(vcpu, p, r,
"trap of EL2 register redirected to EL1");
}
#define EL2_REG(name, acc, rst, v) { \
SYS_DESC(SYS_##name), \
.access = acc, \
.reset = rst, \
.reg = name, \
.visibility = el2_visibility, \
.val = v, \
}
#define EL2_REG_VNCR(name, rst, v) EL2_REG(name, bad_vncr_trap, rst, v)
#define EL2_REG_REDIR(name, rst, v) EL2_REG(name, bad_redir_trap, rst, v)
/*
* Since reset() callback and field val are not used for idregs, they will be
* used for specific purposes for idregs.
* The reset() would return KVM sanitised register value. The value would be the
* same as the host kernel sanitised value if there is no KVM sanitisation.
* The val would be used as a mask indicating writable fields for the idreg.
* Only bits with 1 are writable from userspace. This mask might not be
* necessary in the future whenever all ID registers are enabled as writable
* from userspace.
*/
#define ID_DESC(name) \
SYS_DESC(SYS_##name), \
.access = access_id_reg, \
.get_user = get_id_reg \
/* sys_reg_desc initialiser for known cpufeature ID registers */
#define ID_SANITISED(name) { \
ID_DESC(name), \
.set_user = set_id_reg, \
.visibility = id_visibility, \
.reset = kvm_read_sanitised_id_reg, \
.val = 0, \
}
/* sys_reg_desc initialiser for known cpufeature ID registers */
#define AA32_ID_SANITISED(name) { \
ID_DESC(name), \
.set_user = set_id_reg, \
.visibility = aa32_id_visibility, \
.reset = kvm_read_sanitised_id_reg, \
.val = 0, \
}
/* sys_reg_desc initialiser for writable ID registers */
#define ID_WRITABLE(name, mask) { \
ID_DESC(name), \
.set_user = set_id_reg, \
.visibility = id_visibility, \
.reset = kvm_read_sanitised_id_reg, \
.val = mask, \
}
/*
* sys_reg_desc initialiser for architecturally unallocated cpufeature ID
* register with encoding Op0=3, Op1=0, CRn=0, CRm=crm, Op2=op2
* (1 <= crm < 8, 0 <= Op2 < 8).
*/
#define ID_UNALLOCATED(crm, op2) { \
Op0(3), Op1(0), CRn(0), CRm(crm), Op2(op2), \
.access = access_id_reg, \
.get_user = get_id_reg, \
.set_user = set_id_reg, \
.visibility = raz_visibility, \
.reset = kvm_read_sanitised_id_reg, \
.val = 0, \
}
/*
* sys_reg_desc initialiser for known ID registers that we hide from guests.
* For now, these are exposed just like unallocated ID regs: they appear
* RAZ for the guest.
*/
#define ID_HIDDEN(name) { \
ID_DESC(name), \
.set_user = set_id_reg, \
.visibility = raz_visibility, \
.reset = kvm_read_sanitised_id_reg, \
.val = 0, \
}
static bool access_sp_el1(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (p->is_write)
__vcpu_sys_reg(vcpu, SP_EL1) = p->regval;
else
p->regval = __vcpu_sys_reg(vcpu, SP_EL1);
return true;
}
static bool access_elr(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (p->is_write)
vcpu_write_sys_reg(vcpu, p->regval, ELR_EL1);
else
p->regval = vcpu_read_sys_reg(vcpu, ELR_EL1);
return true;
}
static bool access_spsr(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (p->is_write)
__vcpu_sys_reg(vcpu, SPSR_EL1) = p->regval;
else
p->regval = __vcpu_sys_reg(vcpu, SPSR_EL1);
return true;
}
static bool access_cntkctl_el12(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (p->is_write)
__vcpu_sys_reg(vcpu, CNTKCTL_EL1) = p->regval;
else
p->regval = __vcpu_sys_reg(vcpu, CNTKCTL_EL1);
return true;
}
static u64 reset_hcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
u64 val = r->val;
if (!cpus_have_final_cap(ARM64_HAS_HCR_NV1))
val |= HCR_E2H;
return __vcpu_sys_reg(vcpu, r->reg) = val;
}
static unsigned int sve_el2_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
unsigned int r;
r = el2_visibility(vcpu, rd);
if (r)
return r;
return sve_visibility(vcpu, rd);
}
static bool access_zcr_el2(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
unsigned int vq;
if (guest_hyp_sve_traps_enabled(vcpu)) {
kvm_inject_nested_sve_trap(vcpu);
return true;
}
if (!p->is_write) {
p->regval = vcpu_read_sys_reg(vcpu, ZCR_EL2);
return true;
}
vq = SYS_FIELD_GET(ZCR_ELx, LEN, p->regval) + 1;
vq = min(vq, vcpu_sve_max_vq(vcpu));
vcpu_write_sys_reg(vcpu, vq - 1, ZCR_EL2);
return true;
}
static unsigned int s1poe_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S1POE, IMP))
return 0;
return REG_HIDDEN;
}
/*
* Architected system registers.
* Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
*
* Debug handling: We do trap most, if not all debug related system
* registers. The implementation is good enough to ensure that a guest
* can use these with minimal performance degradation. The drawback is
* that we don't implement any of the external debug architecture.
* This should be revisited if we ever encounter a more demanding
* guest...
*/
static const struct sys_reg_desc sys_reg_descs[] = {
DBG_BCR_BVR_WCR_WVR_EL1(0),
DBG_BCR_BVR_WCR_WVR_EL1(1),
{ SYS_DESC(SYS_MDCCINT_EL1), trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
{ SYS_DESC(SYS_MDSCR_EL1), trap_debug_regs, reset_val, MDSCR_EL1, 0 },
DBG_BCR_BVR_WCR_WVR_EL1(2),
DBG_BCR_BVR_WCR_WVR_EL1(3),
DBG_BCR_BVR_WCR_WVR_EL1(4),
DBG_BCR_BVR_WCR_WVR_EL1(5),
DBG_BCR_BVR_WCR_WVR_EL1(6),
DBG_BCR_BVR_WCR_WVR_EL1(7),
DBG_BCR_BVR_WCR_WVR_EL1(8),
DBG_BCR_BVR_WCR_WVR_EL1(9),
DBG_BCR_BVR_WCR_WVR_EL1(10),
DBG_BCR_BVR_WCR_WVR_EL1(11),
DBG_BCR_BVR_WCR_WVR_EL1(12),
DBG_BCR_BVR_WCR_WVR_EL1(13),
DBG_BCR_BVR_WCR_WVR_EL1(14),
DBG_BCR_BVR_WCR_WVR_EL1(15),
{ SYS_DESC(SYS_MDRAR_EL1), trap_raz_wi },
{ SYS_DESC(SYS_OSLAR_EL1), trap_oslar_el1 },
{ SYS_DESC(SYS_OSLSR_EL1), trap_oslsr_el1, reset_val, OSLSR_EL1,
OSLSR_EL1_OSLM_IMPLEMENTED, .set_user = set_oslsr_el1, },
{ SYS_DESC(SYS_OSDLR_EL1), trap_raz_wi },
{ SYS_DESC(SYS_DBGPRCR_EL1), trap_raz_wi },
{ SYS_DESC(SYS_DBGCLAIMSET_EL1), trap_raz_wi },
{ SYS_DESC(SYS_DBGCLAIMCLR_EL1), trap_raz_wi },
{ SYS_DESC(SYS_DBGAUTHSTATUS_EL1), trap_dbgauthstatus_el1 },
{ SYS_DESC(SYS_MDCCSR_EL0), trap_raz_wi },
{ SYS_DESC(SYS_DBGDTR_EL0), trap_raz_wi },
// DBGDTR[TR]X_EL0 share the same encoding
{ SYS_DESC(SYS_DBGDTRTX_EL0), trap_raz_wi },
{ SYS_DESC(SYS_DBGVCR32_EL2), undef_access, reset_val, DBGVCR32_EL2, 0 },
{ SYS_DESC(SYS_MPIDR_EL1), NULL, reset_mpidr, MPIDR_EL1 },
/*
* ID regs: all ID_SANITISED() entries here must have corresponding
* entries in arm64_ftr_regs[].
*/
/* AArch64 mappings of the AArch32 ID registers */
/* CRm=1 */
AA32_ID_SANITISED(ID_PFR0_EL1),
AA32_ID_SANITISED(ID_PFR1_EL1),
{ SYS_DESC(SYS_ID_DFR0_EL1),
.access = access_id_reg,
.get_user = get_id_reg,
.set_user = set_id_dfr0_el1,
.visibility = aa32_id_visibility,
.reset = read_sanitised_id_dfr0_el1,
.val = ID_DFR0_EL1_PerfMon_MASK |
ID_DFR0_EL1_CopDbg_MASK, },
ID_HIDDEN(ID_AFR0_EL1),
AA32_ID_SANITISED(ID_MMFR0_EL1),
AA32_ID_SANITISED(ID_MMFR1_EL1),
AA32_ID_SANITISED(ID_MMFR2_EL1),
AA32_ID_SANITISED(ID_MMFR3_EL1),
/* CRm=2 */
AA32_ID_SANITISED(ID_ISAR0_EL1),
AA32_ID_SANITISED(ID_ISAR1_EL1),
AA32_ID_SANITISED(ID_ISAR2_EL1),
AA32_ID_SANITISED(ID_ISAR3_EL1),
AA32_ID_SANITISED(ID_ISAR4_EL1),
AA32_ID_SANITISED(ID_ISAR5_EL1),
AA32_ID_SANITISED(ID_MMFR4_EL1),
AA32_ID_SANITISED(ID_ISAR6_EL1),
/* CRm=3 */
AA32_ID_SANITISED(MVFR0_EL1),
AA32_ID_SANITISED(MVFR1_EL1),
AA32_ID_SANITISED(MVFR2_EL1),
ID_UNALLOCATED(3,3),
AA32_ID_SANITISED(ID_PFR2_EL1),
ID_HIDDEN(ID_DFR1_EL1),
AA32_ID_SANITISED(ID_MMFR5_EL1),
ID_UNALLOCATED(3,7),
/* AArch64 ID registers */
/* CRm=4 */
{ SYS_DESC(SYS_ID_AA64PFR0_EL1),
.access = access_id_reg,
.get_user = get_id_reg,
.set_user = set_id_reg,
.reset = read_sanitised_id_aa64pfr0_el1,
.val = ~(ID_AA64PFR0_EL1_AMU |
ID_AA64PFR0_EL1_MPAM |
ID_AA64PFR0_EL1_SVE |
ID_AA64PFR0_EL1_RAS |
ID_AA64PFR0_EL1_AdvSIMD |
ID_AA64PFR0_EL1_FP), },
ID_WRITABLE(ID_AA64PFR1_EL1, ~(ID_AA64PFR1_EL1_PFAR |
ID_AA64PFR1_EL1_DF2 |
ID_AA64PFR1_EL1_MTEX |
ID_AA64PFR1_EL1_THE |
ID_AA64PFR1_EL1_GCS |
ID_AA64PFR1_EL1_MTE_frac |
ID_AA64PFR1_EL1_NMI |
ID_AA64PFR1_EL1_RNDR_trap |
ID_AA64PFR1_EL1_SME |
ID_AA64PFR1_EL1_RES0 |
ID_AA64PFR1_EL1_MPAM_frac |
ID_AA64PFR1_EL1_RAS_frac |
ID_AA64PFR1_EL1_MTE)),
ID_WRITABLE(ID_AA64PFR2_EL1, ID_AA64PFR2_EL1_FPMR),
ID_UNALLOCATED(4,3),
ID_WRITABLE(ID_AA64ZFR0_EL1, ~ID_AA64ZFR0_EL1_RES0),
ID_HIDDEN(ID_AA64SMFR0_EL1),
ID_UNALLOCATED(4,6),
ID_WRITABLE(ID_AA64FPFR0_EL1, ~ID_AA64FPFR0_EL1_RES0),
/* CRm=5 */
{ SYS_DESC(SYS_ID_AA64DFR0_EL1),
.access = access_id_reg,
.get_user = get_id_reg,
.set_user = set_id_aa64dfr0_el1,
.reset = read_sanitised_id_aa64dfr0_el1,
/*
* Prior to FEAT_Debugv8.9, the architecture defines context-aware
* breakpoints (CTX_CMPs) as the highest numbered breakpoints (BRPs).
* KVM does not trap + emulate the breakpoint registers, and as such
* cannot support a layout that misaligns with the underlying hardware.
* While it may be possible to describe a subset that aligns with
* hardware, just prevent changes to BRPs and CTX_CMPs altogether for
* simplicity.
*
* See DDI0487K.a, section D2.8.3 Breakpoint types and linking
* of breakpoints for more details.
*/
.val = ID_AA64DFR0_EL1_DoubleLock_MASK |
ID_AA64DFR0_EL1_WRPs_MASK |
ID_AA64DFR0_EL1_PMUVer_MASK |
ID_AA64DFR0_EL1_DebugVer_MASK, },
ID_SANITISED(ID_AA64DFR1_EL1),
ID_UNALLOCATED(5,2),
ID_UNALLOCATED(5,3),
ID_HIDDEN(ID_AA64AFR0_EL1),
ID_HIDDEN(ID_AA64AFR1_EL1),
ID_UNALLOCATED(5,6),
ID_UNALLOCATED(5,7),
/* CRm=6 */
ID_WRITABLE(ID_AA64ISAR0_EL1, ~ID_AA64ISAR0_EL1_RES0),
ID_WRITABLE(ID_AA64ISAR1_EL1, ~(ID_AA64ISAR1_EL1_GPI |
ID_AA64ISAR1_EL1_GPA |
ID_AA64ISAR1_EL1_API |
ID_AA64ISAR1_EL1_APA)),
ID_WRITABLE(ID_AA64ISAR2_EL1, ~(ID_AA64ISAR2_EL1_RES0 |
ID_AA64ISAR2_EL1_APA3 |
ID_AA64ISAR2_EL1_GPA3)),
ID_UNALLOCATED(6,3),
ID_UNALLOCATED(6,4),
ID_UNALLOCATED(6,5),
ID_UNALLOCATED(6,6),
ID_UNALLOCATED(6,7),
/* CRm=7 */
ID_WRITABLE(ID_AA64MMFR0_EL1, ~(ID_AA64MMFR0_EL1_RES0 |
ID_AA64MMFR0_EL1_TGRAN4_2 |
ID_AA64MMFR0_EL1_TGRAN64_2 |
ID_AA64MMFR0_EL1_TGRAN16_2)),
ID_WRITABLE(ID_AA64MMFR1_EL1, ~(ID_AA64MMFR1_EL1_RES0 |
ID_AA64MMFR1_EL1_HCX |
ID_AA64MMFR1_EL1_TWED |
ID_AA64MMFR1_EL1_XNX |
ID_AA64MMFR1_EL1_VH |
ID_AA64MMFR1_EL1_VMIDBits)),
ID_WRITABLE(ID_AA64MMFR2_EL1, ~(ID_AA64MMFR2_EL1_RES0 |
ID_AA64MMFR2_EL1_EVT |
ID_AA64MMFR2_EL1_FWB |
ID_AA64MMFR2_EL1_IDS |
ID_AA64MMFR2_EL1_NV |
ID_AA64MMFR2_EL1_CCIDX)),
ID_WRITABLE(ID_AA64MMFR3_EL1, (ID_AA64MMFR3_EL1_TCRX |
ID_AA64MMFR3_EL1_S1POE)),
ID_SANITISED(ID_AA64MMFR4_EL1),
ID_UNALLOCATED(7,5),
ID_UNALLOCATED(7,6),
ID_UNALLOCATED(7,7),
{ SYS_DESC(SYS_SCTLR_EL1), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
MTE_REG(RGSR_EL1),
MTE_REG(GCR_EL1),
{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility },
{ SYS_DESC(SYS_TRFCR_EL1), undef_access },
{ SYS_DESC(SYS_SMPRI_EL1), undef_access },
{ SYS_DESC(SYS_SMCR_EL1), undef_access },
{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
{ SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 },
{ SYS_DESC(SYS_TCR_EL1), access_vm_reg, reset_val, TCR_EL1, 0 },
{ SYS_DESC(SYS_TCR2_EL1), access_vm_reg, reset_val, TCR2_EL1, 0 },
PTRAUTH_KEY(APIA),
PTRAUTH_KEY(APIB),
PTRAUTH_KEY(APDA),
PTRAUTH_KEY(APDB),
PTRAUTH_KEY(APGA),
{ SYS_DESC(SYS_SPSR_EL1), access_spsr},
{ SYS_DESC(SYS_ELR_EL1), access_elr},
{ SYS_DESC(SYS_ICC_PMR_EL1), undef_access },
{ SYS_DESC(SYS_AFSR0_EL1), access_vm_reg, reset_unknown, AFSR0_EL1 },
{ SYS_DESC(SYS_AFSR1_EL1), access_vm_reg, reset_unknown, AFSR1_EL1 },
{ SYS_DESC(SYS_ESR_EL1), access_vm_reg, reset_unknown, ESR_EL1 },
{ SYS_DESC(SYS_ERRIDR_EL1), trap_raz_wi },
{ SYS_DESC(SYS_ERRSELR_EL1), trap_raz_wi },
{ SYS_DESC(SYS_ERXFR_EL1), trap_raz_wi },
{ SYS_DESC(SYS_ERXCTLR_EL1), trap_raz_wi },
{ SYS_DESC(SYS_ERXSTATUS_EL1), trap_raz_wi },
{ SYS_DESC(SYS_ERXADDR_EL1), trap_raz_wi },
{ SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi },
{ SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi },
MTE_REG(TFSR_EL1),
MTE_REG(TFSRE0_EL1),
{ SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },
{ SYS_DESC(SYS_PMSCR_EL1), undef_access },
{ SYS_DESC(SYS_PMSNEVFR_EL1), undef_access },
{ SYS_DESC(SYS_PMSICR_EL1), undef_access },
{ SYS_DESC(SYS_PMSIRR_EL1), undef_access },
{ SYS_DESC(SYS_PMSFCR_EL1), undef_access },
{ SYS_DESC(SYS_PMSEVFR_EL1), undef_access },
{ SYS_DESC(SYS_PMSLATFR_EL1), undef_access },
{ SYS_DESC(SYS_PMSIDR_EL1), undef_access },
{ SYS_DESC(SYS_PMBLIMITR_EL1), undef_access },
{ SYS_DESC(SYS_PMBPTR_EL1), undef_access },
{ SYS_DESC(SYS_PMBSR_EL1), undef_access },
/* PMBIDR_EL1 is not trapped */
{ PMU_SYS_REG(PMINTENSET_EL1),
.access = access_pminten, .reg = PMINTENSET_EL1,
.get_user = get_pmreg, .set_user = set_pmreg },
{ PMU_SYS_REG(PMINTENCLR_EL1),
.access = access_pminten, .reg = PMINTENSET_EL1,
.get_user = get_pmreg, .set_user = set_pmreg },
{ SYS_DESC(SYS_PMMIR_EL1), trap_raz_wi },
{ SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
{ SYS_DESC(SYS_PIRE0_EL1), NULL, reset_unknown, PIRE0_EL1 },
{ SYS_DESC(SYS_PIR_EL1), NULL, reset_unknown, PIR_EL1 },
{ SYS_DESC(SYS_POR_EL1), NULL, reset_unknown, POR_EL1,
.visibility = s1poe_visibility },
{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
{ SYS_DESC(SYS_LORSA_EL1), trap_loregion },
{ SYS_DESC(SYS_LOREA_EL1), trap_loregion },
{ SYS_DESC(SYS_LORN_EL1), trap_loregion },
{ SYS_DESC(SYS_LORC_EL1), trap_loregion },
{ SYS_DESC(SYS_LORID_EL1), trap_loregion },
{ SYS_DESC(SYS_VBAR_EL1), access_rw, reset_val, VBAR_EL1, 0 },
{ SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 },
{ SYS_DESC(SYS_ICC_IAR0_EL1), undef_access },
{ SYS_DESC(SYS_ICC_EOIR0_EL1), undef_access },
{ SYS_DESC(SYS_ICC_HPPIR0_EL1), undef_access },
{ SYS_DESC(SYS_ICC_BPR0_EL1), undef_access },
{ SYS_DESC(SYS_ICC_AP0R0_EL1), undef_access },
{ SYS_DESC(SYS_ICC_AP0R1_EL1), undef_access },
{ SYS_DESC(SYS_ICC_AP0R2_EL1), undef_access },
{ SYS_DESC(SYS_ICC_AP0R3_EL1), undef_access },
{ SYS_DESC(SYS_ICC_AP1R0_EL1), undef_access },
{ SYS_DESC(SYS_ICC_AP1R1_EL1), undef_access },
{ SYS_DESC(SYS_ICC_AP1R2_EL1), undef_access },
{ SYS_DESC(SYS_ICC_AP1R3_EL1), undef_access },
{ SYS_DESC(SYS_ICC_DIR_EL1), undef_access },
{ SYS_DESC(SYS_ICC_RPR_EL1), undef_access },
{ SYS_DESC(SYS_ICC_SGI1R_EL1), access_gic_sgi },
{ SYS_DESC(SYS_ICC_ASGI1R_EL1), access_gic_sgi },
{ SYS_DESC(SYS_ICC_SGI0R_EL1), access_gic_sgi },
{ SYS_DESC(SYS_ICC_IAR1_EL1), undef_access },
{ SYS_DESC(SYS_ICC_EOIR1_EL1), undef_access },
{ SYS_DESC(SYS_ICC_HPPIR1_EL1), undef_access },
{ SYS_DESC(SYS_ICC_BPR1_EL1), undef_access },
{ SYS_DESC(SYS_ICC_CTLR_EL1), undef_access },
{ SYS_DESC(SYS_ICC_SRE_EL1), access_gic_sre },
{ SYS_DESC(SYS_ICC_IGRPEN0_EL1), undef_access },
{ SYS_DESC(SYS_ICC_IGRPEN1_EL1), undef_access },
{ SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
{ SYS_DESC(SYS_TPIDR_EL1), NULL, reset_unknown, TPIDR_EL1 },
{ SYS_DESC(SYS_ACCDATA_EL1), undef_access },
{ SYS_DESC(SYS_SCXTNUM_EL1), undef_access },
{ SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0},
{ SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr },
{ SYS_DESC(SYS_CLIDR_EL1), access_clidr, reset_clidr, CLIDR_EL1,
.set_user = set_clidr, .val = ~CLIDR_EL1_RES0 },
{ SYS_DESC(SYS_CCSIDR2_EL1), undef_access },
{ SYS_DESC(SYS_SMIDR_EL1), undef_access },
{ SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 },
ID_WRITABLE(CTR_EL0, CTR_EL0_DIC_MASK |
CTR_EL0_IDC_MASK |
CTR_EL0_DminLine_MASK |
CTR_EL0_IminLine_MASK),
{ SYS_DESC(SYS_SVCR), undef_access, reset_val, SVCR, 0, .visibility = sme_visibility },
{ SYS_DESC(SYS_FPMR), undef_access, reset_val, FPMR, 0, .visibility = fp8_visibility },
{ PMU_SYS_REG(PMCR_EL0), .access = access_pmcr, .reset = reset_pmcr,
.reg = PMCR_EL0, .get_user = get_pmcr, .set_user = set_pmcr },
{ PMU_SYS_REG(PMCNTENSET_EL0),
.access = access_pmcnten, .reg = PMCNTENSET_EL0,
.get_user = get_pmreg, .set_user = set_pmreg },
{ PMU_SYS_REG(PMCNTENCLR_EL0),
.access = access_pmcnten, .reg = PMCNTENSET_EL0,
.get_user = get_pmreg, .set_user = set_pmreg },
{ PMU_SYS_REG(PMOVSCLR_EL0),
.access = access_pmovs, .reg = PMOVSSET_EL0,
.get_user = get_pmreg, .set_user = set_pmreg },
/*
* PM_SWINC_EL0 is exposed to userspace as RAZ/WI, as it was
* previously (and pointlessly) advertised in the past...
*/
{ PMU_SYS_REG(PMSWINC_EL0),
.get_user = get_raz_reg, .set_user = set_wi_reg,
.access = access_pmswinc, .reset = NULL },
{ PMU_SYS_REG(PMSELR_EL0),
.access = access_pmselr, .reset = reset_pmselr, .reg = PMSELR_EL0 },
{ PMU_SYS_REG(PMCEID0_EL0),
.access = access_pmceid, .reset = NULL },
{ PMU_SYS_REG(PMCEID1_EL0),
.access = access_pmceid, .reset = NULL },
{ PMU_SYS_REG(PMCCNTR_EL0),
.access = access_pmu_evcntr, .reset = reset_unknown,
.reg = PMCCNTR_EL0, .get_user = get_pmu_evcntr},
{ PMU_SYS_REG(PMXEVTYPER_EL0),
.access = access_pmu_evtyper, .reset = NULL },
{ PMU_SYS_REG(PMXEVCNTR_EL0),
.access = access_pmu_evcntr, .reset = NULL },
/*
* PMUSERENR_EL0 resets as unknown in 64bit mode while it resets as zero
* in 32bit mode. Here we choose to reset it as zero for consistency.
*/
{ PMU_SYS_REG(PMUSERENR_EL0), .access = access_pmuserenr,
.reset = reset_val, .reg = PMUSERENR_EL0, .val = 0 },
{ PMU_SYS_REG(PMOVSSET_EL0),
.access = access_pmovs, .reg = PMOVSSET_EL0,
.get_user = get_pmreg, .set_user = set_pmreg },
{ SYS_DESC(SYS_POR_EL0), NULL, reset_unknown, POR_EL0,
.visibility = s1poe_visibility },
{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
{ SYS_DESC(SYS_TPIDR2_EL0), undef_access },
{ SYS_DESC(SYS_SCXTNUM_EL0), undef_access },
{ SYS_DESC(SYS_AMCR_EL0), undef_access },
{ SYS_DESC(SYS_AMCFGR_EL0), undef_access },
{ SYS_DESC(SYS_AMCGCR_EL0), undef_access },
{ SYS_DESC(SYS_AMUSERENR_EL0), undef_access },
{ SYS_DESC(SYS_AMCNTENCLR0_EL0), undef_access },
{ SYS_DESC(SYS_AMCNTENSET0_EL0), undef_access },
{ SYS_DESC(SYS_AMCNTENCLR1_EL0), undef_access },
{ SYS_DESC(SYS_AMCNTENSET1_EL0), undef_access },
AMU_AMEVCNTR0_EL0(0),
AMU_AMEVCNTR0_EL0(1),
AMU_AMEVCNTR0_EL0(2),
AMU_AMEVCNTR0_EL0(3),
AMU_AMEVCNTR0_EL0(4),
AMU_AMEVCNTR0_EL0(5),
AMU_AMEVCNTR0_EL0(6),
AMU_AMEVCNTR0_EL0(7),
AMU_AMEVCNTR0_EL0(8),
AMU_AMEVCNTR0_EL0(9),
AMU_AMEVCNTR0_EL0(10),
AMU_AMEVCNTR0_EL0(11),
AMU_AMEVCNTR0_EL0(12),
AMU_AMEVCNTR0_EL0(13),
AMU_AMEVCNTR0_EL0(14),
AMU_AMEVCNTR0_EL0(15),
AMU_AMEVTYPER0_EL0(0),
AMU_AMEVTYPER0_EL0(1),
AMU_AMEVTYPER0_EL0(2),
AMU_AMEVTYPER0_EL0(3),
AMU_AMEVTYPER0_EL0(4),
AMU_AMEVTYPER0_EL0(5),
AMU_AMEVTYPER0_EL0(6),
AMU_AMEVTYPER0_EL0(7),
AMU_AMEVTYPER0_EL0(8),
AMU_AMEVTYPER0_EL0(9),
AMU_AMEVTYPER0_EL0(10),
AMU_AMEVTYPER0_EL0(11),
AMU_AMEVTYPER0_EL0(12),
AMU_AMEVTYPER0_EL0(13),
AMU_AMEVTYPER0_EL0(14),
AMU_AMEVTYPER0_EL0(15),
AMU_AMEVCNTR1_EL0(0),
AMU_AMEVCNTR1_EL0(1),
AMU_AMEVCNTR1_EL0(2),
AMU_AMEVCNTR1_EL0(3),
AMU_AMEVCNTR1_EL0(4),
AMU_AMEVCNTR1_EL0(5),
AMU_AMEVCNTR1_EL0(6),
AMU_AMEVCNTR1_EL0(7),
AMU_AMEVCNTR1_EL0(8),
AMU_AMEVCNTR1_EL0(9),
AMU_AMEVCNTR1_EL0(10),
AMU_AMEVCNTR1_EL0(11),
AMU_AMEVCNTR1_EL0(12),
AMU_AMEVCNTR1_EL0(13),
AMU_AMEVCNTR1_EL0(14),
AMU_AMEVCNTR1_EL0(15),
AMU_AMEVTYPER1_EL0(0),
AMU_AMEVTYPER1_EL0(1),
AMU_AMEVTYPER1_EL0(2),
AMU_AMEVTYPER1_EL0(3),
AMU_AMEVTYPER1_EL0(4),
AMU_AMEVTYPER1_EL0(5),
AMU_AMEVTYPER1_EL0(6),
AMU_AMEVTYPER1_EL0(7),
AMU_AMEVTYPER1_EL0(8),
AMU_AMEVTYPER1_EL0(9),
AMU_AMEVTYPER1_EL0(10),
AMU_AMEVTYPER1_EL0(11),
AMU_AMEVTYPER1_EL0(12),
AMU_AMEVTYPER1_EL0(13),
AMU_AMEVTYPER1_EL0(14),
AMU_AMEVTYPER1_EL0(15),
{ SYS_DESC(SYS_CNTPCT_EL0), access_arch_timer },
{ SYS_DESC(SYS_CNTPCTSS_EL0), access_arch_timer },
{ SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer },
{ SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer },
{ SYS_DESC(SYS_CNTP_CVAL_EL0), access_arch_timer },
/* PMEVCNTRn_EL0 */
PMU_PMEVCNTR_EL0(0),
PMU_PMEVCNTR_EL0(1),
PMU_PMEVCNTR_EL0(2),
PMU_PMEVCNTR_EL0(3),
PMU_PMEVCNTR_EL0(4),
PMU_PMEVCNTR_EL0(5),
PMU_PMEVCNTR_EL0(6),
PMU_PMEVCNTR_EL0(7),
PMU_PMEVCNTR_EL0(8),
PMU_PMEVCNTR_EL0(9),
PMU_PMEVCNTR_EL0(10),
PMU_PMEVCNTR_EL0(11),
PMU_PMEVCNTR_EL0(12),
PMU_PMEVCNTR_EL0(13),
PMU_PMEVCNTR_EL0(14),
PMU_PMEVCNTR_EL0(15),
PMU_PMEVCNTR_EL0(16),
PMU_PMEVCNTR_EL0(17),
PMU_PMEVCNTR_EL0(18),
PMU_PMEVCNTR_EL0(19),
PMU_PMEVCNTR_EL0(20),
PMU_PMEVCNTR_EL0(21),
PMU_PMEVCNTR_EL0(22),
PMU_PMEVCNTR_EL0(23),
PMU_PMEVCNTR_EL0(24),
PMU_PMEVCNTR_EL0(25),
PMU_PMEVCNTR_EL0(26),
PMU_PMEVCNTR_EL0(27),
PMU_PMEVCNTR_EL0(28),
PMU_PMEVCNTR_EL0(29),
PMU_PMEVCNTR_EL0(30),
/* PMEVTYPERn_EL0 */
PMU_PMEVTYPER_EL0(0),
PMU_PMEVTYPER_EL0(1),
PMU_PMEVTYPER_EL0(2),
PMU_PMEVTYPER_EL0(3),
PMU_PMEVTYPER_EL0(4),
PMU_PMEVTYPER_EL0(5),
PMU_PMEVTYPER_EL0(6),
PMU_PMEVTYPER_EL0(7),
PMU_PMEVTYPER_EL0(8),
PMU_PMEVTYPER_EL0(9),
PMU_PMEVTYPER_EL0(10),
PMU_PMEVTYPER_EL0(11),
PMU_PMEVTYPER_EL0(12),
PMU_PMEVTYPER_EL0(13),
PMU_PMEVTYPER_EL0(14),
PMU_PMEVTYPER_EL0(15),
PMU_PMEVTYPER_EL0(16),
PMU_PMEVTYPER_EL0(17),
PMU_PMEVTYPER_EL0(18),
PMU_PMEVTYPER_EL0(19),
PMU_PMEVTYPER_EL0(20),
PMU_PMEVTYPER_EL0(21),
PMU_PMEVTYPER_EL0(22),
PMU_PMEVTYPER_EL0(23),
PMU_PMEVTYPER_EL0(24),
PMU_PMEVTYPER_EL0(25),
PMU_PMEVTYPER_EL0(26),
PMU_PMEVTYPER_EL0(27),
PMU_PMEVTYPER_EL0(28),
PMU_PMEVTYPER_EL0(29),
PMU_PMEVTYPER_EL0(30),
/*
* PMCCFILTR_EL0 resets as unknown in 64bit mode while it resets as zero
* in 32bit mode. Here we choose to reset it as zero for consistency.
*/
{ PMU_SYS_REG(PMCCFILTR_EL0), .access = access_pmu_evtyper,
.reset = reset_val, .reg = PMCCFILTR_EL0, .val = 0 },
EL2_REG_VNCR(VPIDR_EL2, reset_unknown, 0),
EL2_REG_VNCR(VMPIDR_EL2, reset_unknown, 0),
EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1),
EL2_REG(ACTLR_EL2, access_rw, reset_val, 0),
EL2_REG_VNCR(HCR_EL2, reset_hcr, 0),
EL2_REG(MDCR_EL2, access_rw, reset_val, 0),
EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1),
EL2_REG_VNCR(HSTR_EL2, reset_val, 0),
EL2_REG_VNCR(HFGRTR_EL2, reset_val, 0),
EL2_REG_VNCR(HFGWTR_EL2, reset_val, 0),
EL2_REG_VNCR(HFGITR_EL2, reset_val, 0),
EL2_REG_VNCR(HACR_EL2, reset_val, 0),
{ SYS_DESC(SYS_ZCR_EL2), .access = access_zcr_el2, .reset = reset_val,
.visibility = sve_el2_visibility, .reg = ZCR_EL2 },
EL2_REG_VNCR(HCRX_EL2, reset_val, 0),
EL2_REG(TTBR0_EL2, access_rw, reset_val, 0),
EL2_REG(TTBR1_EL2, access_rw, reset_val, 0),
EL2_REG(TCR_EL2, access_rw, reset_val, TCR_EL2_RES1),
EL2_REG_VNCR(VTTBR_EL2, reset_val, 0),
EL2_REG_VNCR(VTCR_EL2, reset_val, 0),
{ SYS_DESC(SYS_DACR32_EL2), undef_access, reset_unknown, DACR32_EL2 },
EL2_REG_VNCR(HDFGRTR_EL2, reset_val, 0),
EL2_REG_VNCR(HDFGWTR_EL2, reset_val, 0),
EL2_REG_VNCR(HAFGRTR_EL2, reset_val, 0),
EL2_REG_REDIR(SPSR_EL2, reset_val, 0),
EL2_REG_REDIR(ELR_EL2, reset_val, 0),
{ SYS_DESC(SYS_SP_EL1), access_sp_el1},
/* AArch32 SPSR_* are RES0 if trapped from a NV guest */
{ SYS_DESC(SYS_SPSR_irq), .access = trap_raz_wi },
{ SYS_DESC(SYS_SPSR_abt), .access = trap_raz_wi },
{ SYS_DESC(SYS_SPSR_und), .access = trap_raz_wi },
{ SYS_DESC(SYS_SPSR_fiq), .access = trap_raz_wi },
{ SYS_DESC(SYS_IFSR32_EL2), undef_access, reset_unknown, IFSR32_EL2 },
EL2_REG(AFSR0_EL2, access_rw, reset_val, 0),
EL2_REG(AFSR1_EL2, access_rw, reset_val, 0),
EL2_REG_REDIR(ESR_EL2, reset_val, 0),
{ SYS_DESC(SYS_FPEXC32_EL2), undef_access, reset_val, FPEXC32_EL2, 0x700 },
EL2_REG_REDIR(FAR_EL2, reset_val, 0),
EL2_REG(HPFAR_EL2, access_rw, reset_val, 0),
EL2_REG(MAIR_EL2, access_rw, reset_val, 0),
EL2_REG(AMAIR_EL2, access_rw, reset_val, 0),
EL2_REG(VBAR_EL2, access_rw, reset_val, 0),
EL2_REG(RVBAR_EL2, access_rw, reset_val, 0),
{ SYS_DESC(SYS_RMR_EL2), undef_access },
EL2_REG_VNCR(ICH_HCR_EL2, reset_val, 0),
EL2_REG(CONTEXTIDR_EL2, access_rw, reset_val, 0),
EL2_REG(TPIDR_EL2, access_rw, reset_val, 0),
EL2_REG_VNCR(CNTVOFF_EL2, reset_val, 0),
EL2_REG(CNTHCTL_EL2, access_rw, reset_val, 0),
{ SYS_DESC(SYS_CNTKCTL_EL12), access_cntkctl_el12 },
EL2_REG(SP_EL2, NULL, reset_unknown, 0),
};
static bool handle_at_s1e01(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u32 op = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
__kvm_at_s1e01(vcpu, op, p->regval);
return true;
}
static bool handle_at_s1e2(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u32 op = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
/* There is no FGT associated with AT S1E2A :-( */
if (op == OP_AT_S1E2A &&
!kvm_has_feat(vcpu->kvm, ID_AA64ISAR2_EL1, ATS1A, IMP)) {
kvm_inject_undefined(vcpu);
return false;
}
__kvm_at_s1e2(vcpu, op, p->regval);
return true;
}
static bool handle_at_s12(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u32 op = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
__kvm_at_s12(vcpu, op, p->regval);
return true;
}
static bool kvm_supported_tlbi_s12_op(struct kvm_vcpu *vpcu, u32 instr)
{
struct kvm *kvm = vpcu->kvm;
u8 CRm = sys_reg_CRm(instr);
if (sys_reg_CRn(instr) == TLBI_CRn_nXS &&
!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP))
return false;
if (CRm == TLBI_CRm_nROS &&
!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
return false;
return true;
}
static bool handle_alle1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
if (!kvm_supported_tlbi_s12_op(vcpu, sys_encoding))
return undef_access(vcpu, p, r);
write_lock(&vcpu->kvm->mmu_lock);
/*
* Drop all shadow S2s, resulting in S1/S2 TLBIs for each of the
* corresponding VMIDs.
*/
kvm_nested_s2_unmap(vcpu->kvm, true);
write_unlock(&vcpu->kvm->mmu_lock);
return true;
}
static bool kvm_supported_tlbi_ipas2_op(struct kvm_vcpu *vpcu, u32 instr)
{
struct kvm *kvm = vpcu->kvm;
u8 CRm = sys_reg_CRm(instr);
u8 Op2 = sys_reg_Op2(instr);
if (sys_reg_CRn(instr) == TLBI_CRn_nXS &&
!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP))
return false;
if (CRm == TLBI_CRm_IPAIS && (Op2 == 2 || Op2 == 6) &&
!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
return false;
if (CRm == TLBI_CRm_IPAONS && (Op2 == 0 || Op2 == 4) &&
!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
return false;
if (CRm == TLBI_CRm_IPAONS && (Op2 == 3 || Op2 == 7) &&
!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
return false;
return true;
}
/* Only defined here as this is an internal "abstraction" */
union tlbi_info {
struct {
u64 start;
u64 size;
} range;
struct {
u64 addr;
} ipa;
struct {
u64 addr;
u32 encoding;
} va;
};
static void s2_mmu_unmap_range(struct kvm_s2_mmu *mmu,
const union tlbi_info *info)
{
/*
* The unmap operation is allowed to drop the MMU lock and block, which
* means that @mmu could be used for a different context than the one
* currently being invalidated.
*
* This behavior is still safe, as:
*
* 1) The vCPU(s) that recycled the MMU are responsible for invalidating
* the entire MMU before reusing it, which still honors the intent
* of a TLBI.
*
* 2) Until the guest TLBI instruction is 'retired' (i.e. increment PC
* and ERET to the guest), other vCPUs are allowed to use stale
* translations.
*
* 3) Accidentally unmapping an unrelated MMU context is nonfatal, and
* at worst may cause more aborts for shadow stage-2 fills.
*
* Dropping the MMU lock also implies that shadow stage-2 fills could
* happen behind the back of the TLBI. This is still safe, though, as
* the L1 needs to put its stage-2 in a consistent state before doing
* the TLBI.
*/
kvm_stage2_unmap_range(mmu, info->range.start, info->range.size, true);
}
static bool handle_vmalls12e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
u64 limit, vttbr;
if (!kvm_supported_tlbi_s12_op(vcpu, sys_encoding))
return undef_access(vcpu, p, r);
vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
limit = BIT_ULL(kvm_get_pa_bits(vcpu->kvm));
kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr),
&(union tlbi_info) {
.range = {
.start = 0,
.size = limit,
},
},
s2_mmu_unmap_range);
return true;
}
static bool handle_ripas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
u64 base, range, tg, num, scale;
int shift;
if (!kvm_supported_tlbi_ipas2_op(vcpu, sys_encoding))
return undef_access(vcpu, p, r);
/*
* Because the shadow S2 structure doesn't necessarily reflect that
* of the guest's S2 (different base granule size, for example), we
* decide to ignore TTL and only use the described range.
*/
tg = FIELD_GET(GENMASK(47, 46), p->regval);
scale = FIELD_GET(GENMASK(45, 44), p->regval);
num = FIELD_GET(GENMASK(43, 39), p->regval);
base = p->regval & GENMASK(36, 0);
switch(tg) {
case 1:
shift = 12;
break;
case 2:
shift = 14;
break;
case 3:
default: /* IMPDEF: handle tg==0 as 64k */
shift = 16;